agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH v2a 3/4] Add alias to be used as "unset" state. 40+ messages / 2 participants [nested] [flat]
* [PATCH v2a 3/4] Add alias to be used as "unset" state. @ 2025-09-04 16:22 Nikolay Shaplov <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Nikolay Shaplov @ 2025-09-04 16:22 UTC (permalink / raw) Add `unset_alias` string parameter to ternary reloption definition. This will allow user explicitly switch ternary option to "unset" state. Use this feature to implement `vacuum_index_cleanup` and gist's `buffering` reloptions as ternary reloptions --- src/backend/access/common/reloptions.c | 91 +++++++++++--------------- src/backend/access/gist/gistbuild.c | 4 +- src/backend/commands/vacuum.c | 11 ++-- src/include/access/gist_private.h | 10 +-- src/include/access/reloptions.h | 7 +- src/include/utils/rel.h | 10 +-- src/test/regress/expected/gist.out | 3 +- 7 files changed, 54 insertions(+), 82 deletions(-) diff --git a/src/backend/access/common/reloptions.c b/src/backend/access/common/reloptions.c index f543f11001..3637646641 100644 --- a/src/backend/access/common/reloptions.c +++ b/src/backend/access/common/reloptions.c @@ -170,6 +170,27 @@ static relopt_ternary ternaryRelOpts[] = RELOPT_KIND_HEAP | RELOPT_KIND_TOAST, ShareUpdateExclusiveLock }, + NULL, + TERNARY_UNSET + }, + { + { + "vacuum_index_cleanup", + "Controls index vacuuming and index cleanup", + RELOPT_KIND_HEAP | RELOPT_KIND_TOAST, + ShareUpdateExclusiveLock + }, + "auto", + TERNARY_UNSET + }, + { + { + "buffering", + "Enables buffering build for this GiST index", + RELOPT_KIND_GIST, + AccessExclusiveLock + }, + "auto", TERNARY_UNSET }, /* list terminator */ @@ -489,30 +510,6 @@ static relopt_real realRelOpts[] = {{NULL}} }; -/* values from StdRdOptIndexCleanup */ -static relopt_enum_elt_def StdRdOptIndexCleanupValues[] = -{ - {"auto", STDRD_OPTION_VACUUM_INDEX_CLEANUP_AUTO}, - {"on", STDRD_OPTION_VACUUM_INDEX_CLEANUP_ON}, - {"off", STDRD_OPTION_VACUUM_INDEX_CLEANUP_OFF}, - {"true", STDRD_OPTION_VACUUM_INDEX_CLEANUP_ON}, - {"false", STDRD_OPTION_VACUUM_INDEX_CLEANUP_OFF}, - {"yes", STDRD_OPTION_VACUUM_INDEX_CLEANUP_ON}, - {"no", STDRD_OPTION_VACUUM_INDEX_CLEANUP_OFF}, - {"1", STDRD_OPTION_VACUUM_INDEX_CLEANUP_ON}, - {"0", STDRD_OPTION_VACUUM_INDEX_CLEANUP_OFF}, - {(const char *) NULL} /* list terminator */ -}; - -/* values from GistOptBufferingMode */ -static relopt_enum_elt_def gistBufferingOptValues[] = -{ - {"auto", GIST_OPTION_BUFFERING_AUTO}, - {"on", GIST_OPTION_BUFFERING_ON}, - {"off", GIST_OPTION_BUFFERING_OFF}, - {(const char *) NULL} /* list terminator */ -}; - /* values from ViewOptCheckOption */ static relopt_enum_elt_def viewCheckOptValues[] = { @@ -524,28 +521,6 @@ static relopt_enum_elt_def viewCheckOptValues[] = static relopt_enum enumRelOpts[] = { - { - { - "vacuum_index_cleanup", - "Controls index vacuuming and index cleanup", - RELOPT_KIND_HEAP | RELOPT_KIND_TOAST, - ShareUpdateExclusiveLock - }, - StdRdOptIndexCleanupValues, - STDRD_OPTION_VACUUM_INDEX_CLEANUP_AUTO, - gettext_noop("Valid values are \"on\", \"off\", and \"auto\".") - }, - { - { - "buffering", - "Enables buffering build for this GiST index", - RELOPT_KIND_GIST, - AccessExclusiveLock - }, - gistBufferingOptValues, - GIST_OPTION_BUFFERING_AUTO, - gettext_noop("Valid values are \"on\", \"off\", and \"auto\".") - }, { { "check_option", @@ -913,13 +888,14 @@ add_local_bool_reloption(local_relopts *relopts, const char *name, */ static relopt_ternary * init_ternary_reloption(bits32 kinds, const char *name, const char *desc, - ternary default_val, LOCKMODE lockmode) + ternary default_val, const char* unset_alias, LOCKMODE lockmode) { relopt_ternary *newoption; newoption = (relopt_ternary *) allocate_reloption(kinds, RELOPT_TYPE_TERNARY, name, desc, lockmode); newoption->default_val = default_val; + newoption->unset_alias = unset_alias; return newoption; } @@ -930,10 +906,10 @@ init_ternary_reloption(bits32 kinds, const char *name, const char *desc, */ void add_ternary_reloption(bits32 kinds, const char *name, const char *desc, - ternary default_val, LOCKMODE lockmode) + ternary default_val, const char* unset_alias, LOCKMODE lockmode) { relopt_ternary *newoption = init_ternary_reloption(kinds, name, desc, - default_val, lockmode); + default_val, unset_alias, lockmode); add_reloption((relopt_gen *) newoption); } @@ -947,11 +923,11 @@ add_ternary_reloption(bits32 kinds, const char *name, const char *desc, void add_local_ternary_reloption(local_relopts *relopts, const char *name, const char *desc, ternary default_val, - int offset) + const char* unset_alias, int offset) { relopt_ternary *newoption = init_ternary_reloption(RELOPT_KIND_LOCAL, name, desc, - default_val, 0); + default_val, unset_alias, 0); add_local_reloption(relopts, (relopt_gen *) newoption, offset); } @@ -1692,8 +1668,19 @@ parse_one_reloption(relopt_value *option, char *text_str, int text_len, case RELOPT_TYPE_TERNARY: { bool b; + relopt_ternary *opt = (relopt_ternary *) option->gen; + parsed = parse_bool(value, &b); option->values.ternary_val = b ? TERNARY_TRUE : TERNARY_FALSE; + + if (!parsed && opt->unset_alias) + { + if (pg_strcasecmp(value, opt->unset_alias) == 0) + { + option->values.ternary_val = TERNARY_UNSET; + parsed = true; + } + } if (validate && !parsed) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), @@ -1988,7 +1975,7 @@ default_reloptions(Datum reloptions, bool validate, relopt_kind kind) offsetof(StdRdOptions, user_catalog_table)}, {"parallel_workers", RELOPT_TYPE_INT, offsetof(StdRdOptions, parallel_workers)}, - {"vacuum_index_cleanup", RELOPT_TYPE_ENUM, + {"vacuum_index_cleanup", RELOPT_TYPE_TERNARY, offsetof(StdRdOptions, vacuum_index_cleanup)}, {"vacuum_truncate", RELOPT_TYPE_TERNARY, offsetof(StdRdOptions, vacuum_truncate)}, diff --git a/src/backend/access/gist/gistbuild.c b/src/backend/access/gist/gistbuild.c index 9b2ec9815f..7f641f7825 100644 --- a/src/backend/access/gist/gistbuild.c +++ b/src/backend/access/gist/gistbuild.c @@ -213,9 +213,9 @@ gistbuild(Relation heap, Relation index, IndexInfo *indexInfo) */ if (options) { - if (options->buffering_mode == GIST_OPTION_BUFFERING_ON) + if (options->buffering_mode == TERNARY_TRUE) buildstate.buildMode = GIST_BUFFERING_STATS; - else if (options->buffering_mode == GIST_OPTION_BUFFERING_OFF) + else if (options->buffering_mode == TERNARY_FALSE) buildstate.buildMode = GIST_BUFFERING_DISABLED; else /* must be "auto" */ buildstate.buildMode = GIST_BUFFERING_AUTO; diff --git a/src/backend/commands/vacuum.c b/src/backend/commands/vacuum.c index 977babff54..61b4bdb682 100644 --- a/src/backend/commands/vacuum.c +++ b/src/backend/commands/vacuum.c @@ -2175,22 +2175,21 @@ vacuum_rel(Oid relid, RangeVar *relation, VacuumParams params, */ if (params.index_cleanup == VACOPTVALUE_UNSPECIFIED) { - StdRdOptIndexCleanup vacuum_index_cleanup; + ternary vacuum_index_cleanup; if (rel->rd_options == NULL) - vacuum_index_cleanup = STDRD_OPTION_VACUUM_INDEX_CLEANUP_AUTO; + vacuum_index_cleanup = TERNARY_UNSET; else vacuum_index_cleanup = ((StdRdOptions *) rel->rd_options)->vacuum_index_cleanup; - if (vacuum_index_cleanup == STDRD_OPTION_VACUUM_INDEX_CLEANUP_AUTO) + if (vacuum_index_cleanup == TERNARY_UNSET) params.index_cleanup = VACOPTVALUE_AUTO; - else if (vacuum_index_cleanup == STDRD_OPTION_VACUUM_INDEX_CLEANUP_ON) + else if (vacuum_index_cleanup == TERNARY_TRUE) params.index_cleanup = VACOPTVALUE_ENABLED; else { - Assert(vacuum_index_cleanup == - STDRD_OPTION_VACUUM_INDEX_CLEANUP_OFF); + Assert(vacuum_index_cleanup == TERNARY_FALSE); params.index_cleanup = VACOPTVALUE_DISABLED; } } diff --git a/src/include/access/gist_private.h b/src/include/access/gist_private.h index 39404ec7cd..a931c988fb 100644 --- a/src/include/access/gist_private.h +++ b/src/include/access/gist_private.h @@ -380,14 +380,6 @@ typedef struct GISTBuildBuffers int rootlevel; } GISTBuildBuffers; -/* GiSTOptions->buffering_mode values */ -typedef enum GistOptBufferingMode -{ - GIST_OPTION_BUFFERING_AUTO, - GIST_OPTION_BUFFERING_ON, - GIST_OPTION_BUFFERING_OFF, -} GistOptBufferingMode; - /* * Storage type for GiST's reloptions */ @@ -395,7 +387,7 @@ typedef struct GiSTOptions { int32 vl_len_; /* varlena header (do not touch directly!) */ int fillfactor; /* page fill factor in percent (0..100) */ - GistOptBufferingMode buffering_mode; /* buffering build mode */ + ternary buffering_mode; /* buffering build mode */ } GiSTOptions; /* gist.c */ diff --git a/src/include/access/reloptions.h b/src/include/access/reloptions.h index a436697658..552c89869f 100644 --- a/src/include/access/reloptions.h +++ b/src/include/access/reloptions.h @@ -99,6 +99,7 @@ typedef struct relopt_bool typedef struct relopt_rernary { relopt_gen gen; + const char *unset_alias; /* word that will be treated as unset value */ int default_val; } relopt_ternary; @@ -191,7 +192,8 @@ extern relopt_kind add_reloption_kind(void); extern void add_bool_reloption(bits32 kinds, const char *name, const char *desc, bool default_val, LOCKMODE lockmode); extern void add_ternary_reloption(bits32 kinds, const char *name, - const char *desc, int default_val, LOCKMODE lockmode); + const char *desc, ternary default_val, + const char* unset_alias, LOCKMODE lockmode); extern void add_int_reloption(bits32 kinds, const char *name, const char *desc, int default_val, int min_val, int max_val, LOCKMODE lockmode); @@ -213,7 +215,8 @@ extern void add_local_bool_reloption(local_relopts *relopts, const char *name, int offset); extern void add_local_ternary_reloption(local_relopts *relopts, const char *name, const char *desc, - ternary default_val, int offset); + ternary default_val, const char* unset_alias, + int offset); extern void add_local_int_reloption(local_relopts *relopts, const char *name, const char *desc, int default_val, int min_val, int max_val, int offset); diff --git a/src/include/utils/rel.h b/src/include/utils/rel.h index 7346d618f9..95a18c6d16 100644 --- a/src/include/utils/rel.h +++ b/src/include/utils/rel.h @@ -329,14 +329,6 @@ typedef struct AutoVacOpts float8 analyze_scale_factor; } AutoVacOpts; -/* StdRdOptions->vacuum_index_cleanup values */ -typedef enum StdRdOptIndexCleanup -{ - STDRD_OPTION_VACUUM_INDEX_CLEANUP_AUTO = 0, - STDRD_OPTION_VACUUM_INDEX_CLEANUP_OFF, - STDRD_OPTION_VACUUM_INDEX_CLEANUP_ON, -} StdRdOptIndexCleanup; - typedef struct StdRdOptions { int32 vl_len_; /* varlena header (do not touch directly!) */ @@ -345,7 +337,7 @@ typedef struct StdRdOptions AutoVacOpts autovacuum; /* autovacuum-related options */ bool user_catalog_table; /* use as an additional catalog relation */ int parallel_workers; /* max number of parallel workers */ - StdRdOptIndexCleanup vacuum_index_cleanup; /* controls index vacuuming */ + ternary vacuum_index_cleanup; /* controls index vacuuming */ ternary vacuum_truncate; /* enables vacuum to truncate a relation */ /* diff --git a/src/test/regress/expected/gist.out b/src/test/regress/expected/gist.out index c75bbb23b6..76751d1859 100644 --- a/src/test/regress/expected/gist.out +++ b/src/test/regress/expected/gist.out @@ -12,8 +12,7 @@ create index gist_pointidx4 on gist_point_tbl using gist(p) with (buffering = au drop index gist_pointidx2, gist_pointidx3, gist_pointidx4; -- Make sure bad values are refused create index gist_pointidx5 on gist_point_tbl using gist(p) with (buffering = invalid_value); -ERROR: invalid value for enum option "buffering": invalid_value -DETAIL: Valid values are "on", "off", and "auto". +ERROR: invalid value for ternary option "buffering": invalid_value create index gist_pointidx5 on gist_point_tbl using gist(p) with (fillfactor=9); ERROR: value 9 out of bounds for option "fillfactor" DETAIL: Valid values are between "10" and "100". -- 2.39.2 --nextPart4155600.3ZeAukHxDK Content-Disposition: attachment; filename="v2a-0004-Extra-tests.patch" Content-Transfer-Encoding: 7Bit Content-Type: text/x-patch; charset="unicode-2-0-utf-8"; name="v2a-0004-Extra-tests.patch" ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 40+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * The first file exported by the decoding worker must contain a snapshot, the - * following ones contain the data changes. - */ -#define WORKER_FILE_SNAPSHOT 0 - -/* - * Information needed to apply concurrent data changes. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + +/* + * Information needed to apply concurrent data changes. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 40+ messages in thread
end of thread, other threads:[~2026-07-15 08:37 UTC | newest] Thread overview: 40+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2025-09-04 16:22 [PATCH v2a 3/4] Add alias to be used as "unset" state. Nikolay Shaplov <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox