agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH v20 3/3] Add Assert guard to detect permission check before lock regressions 44+ messages / 2 participants [nested] [flat]
* [PATCH v20 3/3] Add Assert guard to detect permission check before lock regressions @ 2026-04-27 14:23 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 44+ messages in thread From: Bertrand Drouvot @ 2026-04-27 14:23 UTC (permalink / raw) Add instrumentation under USE_ASSERT_CHECKING to detect cases where object_aclcheck() is called on a referenced object before a lock is held on it, which would widen the TOCTOU window between the permission check and the dependency recording. In recordMultipleDependencies() and changeDependencyFor(), for each referenced object that had a permission check earlier in the same statement, assert that a lock is already held. This catches any future code that adds a permission check on a referenced object without first acquiring a lock. The tracking records each (classId, objectId, mode) from object_aclcheck() and pg_class_aclcheck(), filtering to only dependency-relevant ACL modes (ACL_CREATE, ACL_USAGE on non namespaces, ACL_EXECUTE, ACL_TRIGGER, ACL_REFERENCES). Tracking resets at each ProcessUtility() call. The tracking array is capped at 1024 entries per statement, which is sufficient for any practical DDL command. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/[email protected] --- src/backend/catalog/aclchk.c | 32 ++++++++++++ src/backend/catalog/pg_depend.c | 52 ++++++++++++++++++++ src/backend/tcop/utility.c | 3 ++ src/include/catalog/aclcheck_track.h | 73 ++++++++++++++++++++++++++++ src/tools/pgindent/typedefs.list | 1 + 5 files changed, 161 insertions(+) 51.5% src/backend/catalog/ 46.7% src/include/catalog/ diff --git a/src/backend/catalog/aclchk.c b/src/backend/catalog/aclchk.c index 67424fe3b0c..3c3b35910e1 100644 --- a/src/backend/catalog/aclchk.c +++ b/src/backend/catalog/aclchk.c @@ -76,6 +76,7 @@ #include "parser/parse_type.h" #include "storage/lmgr.h" #include "utils/acl.h" +#include "catalog/aclcheck_track.h" #include "utils/aclchk_internal.h" #include "utils/builtins.h" #include "utils/fmgroids.h" @@ -3890,6 +3891,8 @@ object_aclcheck_ext(Oid classid, Oid objectid, Oid roleid, AclMode mode, bool *is_missing) { + aclcheck_track_record(classid, objectid, mode); + if (object_aclmask_ext(classid, objectid, roleid, mode, ACLMASK_ANY, is_missing) != 0) return ACLCHECK_OK; @@ -4092,6 +4095,8 @@ AclResult pg_class_aclcheck_ext(Oid table_oid, Oid roleid, AclMode mode, bool *is_missing) { + aclcheck_track_record(RelationRelationId, table_oid, mode); + if (pg_class_aclmask_ext(table_oid, roleid, mode, ACLMASK_ANY, is_missing) != 0) return ACLCHECK_OK; @@ -5035,3 +5040,30 @@ RemoveRoleFromInitPriv(Oid roleid, Oid classid, Oid objid, int32 objsubid) table_close(rel, RowExclusiveLock); } + +/* + * Instrumentation to detect permission check before lock regressions. + * Only used in assert-enabled builds. + */ +#ifdef USE_ASSERT_CHECKING +AclCheckEntry aclcheck_tracked[ACLCHECK_TRACK_MAX]; +int aclcheck_tracked_count = 0; + +void +aclcheck_track_reset(void) +{ + aclcheck_tracked_count = 0; +} + +bool +aclcheck_track_was_checked(Oid classId, Oid objectId) +{ + for (int i = 0; i < aclcheck_tracked_count; i++) + { + if (aclcheck_tracked[i].classId == classId && + aclcheck_tracked[i].objectId == objectId) + return true; + } + return false; +} +#endif /* USE_ASSERT_CHECKING */ diff --git a/src/backend/catalog/pg_depend.c b/src/backend/catalog/pg_depend.c index 5618e3d26fa..28fa99b2d42 100644 --- a/src/backend/catalog/pg_depend.c +++ b/src/backend/catalog/pg_depend.c @@ -18,6 +18,7 @@ #include "access/htup_details.h" #include "access/table.h" #include "catalog/catalog.h" +#include "catalog/aclcheck_track.h" #include "catalog/dependency.h" #include "catalog/indexing.h" #include "catalog/pg_constraint.h" @@ -27,6 +28,8 @@ #include "catalog/partition.h" #include "commands/extension.h" #include "miscadmin.h" +#include "storage/lmgr.h" +#include "storage/lock.h" #include "utils/fmgroids.h" #include "utils/lsyscache.h" #include "utils/rel.h" @@ -107,6 +110,31 @@ recordMultipleDependencies(const ObjectAddress *depender, if (isObjectPinned(referenced)) continue; +#ifdef USE_ASSERT_CHECKING + /* + * If this referenced object had a permission check earlier in this + * statement, assert that a lock is already held on it. This ensures + * callers acquired the lock before calling object_aclcheck(), not + * after. The latter would widen the TOCTOU window between the + * permission check and the dependency recording. + */ + if (aclcheck_track_was_checked(referenced->classId, referenced->objectId)) + { + if (referenced->classId == RelationRelationId) + Assert(CheckRelationOidLockedByMe(referenced->objectId, + AccessShareLock, true)); + else + { + LOCKTAG tag; + + SET_LOCKTAG_OBJECT(tag, MyDatabaseId, + referenced->classId, + referenced->objectId, 0); + Assert(LockHeldByMe(&tag, AccessShareLock, true)); + } + } +#endif + /* * Acquire a lock and check object still exists while recording the * dependency. @@ -511,6 +539,30 @@ changeDependencyFor(Oid classId, Oid objectId, return 1; } +#ifdef USE_ASSERT_CHECKING + /* + * If this referenced object had a permission check earlier in this + * statement, assert that a lock is already held on it. This ensures + * callers acquired the lock before calling object_aclcheck(), not after. + * The latter would widen the TOCTOU window between the permission check and + * the dependency recording. + */ + if (aclcheck_track_was_checked(objAddr.classId, objAddr.objectId)) + { + if (objAddr.classId == RelationRelationId) + Assert(CheckRelationOidLockedByMe(objAddr.objectId, + AccessShareLock, true)); + else + { + LOCKTAG tag; + + SET_LOCKTAG_OBJECT(tag, MyDatabaseId, + objAddr.classId, + objAddr.objectId, 0); + Assert(LockHeldByMe(&tag, AccessShareLock, true)); + } + } +#endif /* * Acquire a lock and check object still exists while changing the * dependency. diff --git a/src/backend/tcop/utility.c b/src/backend/tcop/utility.c index 73a56f1df1d..0c4d382bd37 100644 --- a/src/backend/tcop/utility.c +++ b/src/backend/tcop/utility.c @@ -21,6 +21,7 @@ #include "access/xact.h" #include "access/xlog.h" #include "catalog/namespace.h" +#include "catalog/aclcheck_track.h" #include "catalog/pg_authid.h" #include "catalog/pg_inherits.h" #include "catalog/toasting.h" @@ -515,6 +516,8 @@ ProcessUtility(PlannedStmt *pstmt, Assert(queryString != NULL); /* required as of 8.4 */ Assert(qc == NULL || qc->commandTag == CMDTAG_UNKNOWN); + aclcheck_track_reset(); + /* * We provide a function hook variable that lets loadable plugins get * control when ProcessUtility is called. Such a plugin would normally diff --git a/src/include/catalog/aclcheck_track.h b/src/include/catalog/aclcheck_track.h new file mode 100644 index 00000000000..5825d7398d3 --- /dev/null +++ b/src/include/catalog/aclcheck_track.h @@ -0,0 +1,73 @@ +/*------------------------------------------------------------------------- + * + * aclcheck_track.h + * Instrumentation to detect permission check before lock via Assert in + * recordMultipleDependencies() and changeDependencyFor(). + * + * Only active in USE_ASSERT_CHECKING builds. + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/catalog/aclcheck_track.h + * + *------------------------------------------------------------------------- + */ +#ifndef ACLCHECK_TRACK_H +#define ACLCHECK_TRACK_H + +#ifdef USE_ASSERT_CHECKING + +#include "catalog/pg_namespace.h" + +#define ACLCHECK_TRACK_MAX 1024 + +typedef struct AclCheckEntry +{ + Oid classId; + Oid objectId; +} AclCheckEntry; + +extern AclCheckEntry aclcheck_tracked[]; +extern int aclcheck_tracked_count; + +extern void aclcheck_track_reset(void); +extern bool aclcheck_track_was_checked(Oid classId, Oid objectId); + +/* + * Only record aclchecks that are dependency-relevant: + * - ACL_CREATE on any object (creating something in a container) + * - ACL_USAGE on non-namespace objects (using a type, language, server) + * - ACL_EXECUTE on functions + * - ACL_TRIGGER, ACL_REFERENCES on relations + * + * Skip ACL_USAGE on namespaces — that's name resolution, not dependency. + */ +static inline void +aclcheck_track_record(Oid classId, Oid objectId, AclMode mode) +{ + /* Skip ACL_USAGE on namespaces (name resolution, not dependency) */ + if (classId == NamespaceRelationId && !(mode & ACL_CREATE)) + return; + + /* Only track dependency-relevant modes */ + if (!(mode & (ACL_CREATE | ACL_USAGE | ACL_EXECUTE | ACL_TRIGGER | ACL_REFERENCES))) + return; + + if (aclcheck_tracked_count < ACLCHECK_TRACK_MAX) + { + aclcheck_tracked[aclcheck_tracked_count].classId = classId; + aclcheck_tracked[aclcheck_tracked_count].objectId = objectId; + aclcheck_tracked_count++; + } +} + +#else /* !USE_ASSERT_CHECKING */ + +#define aclcheck_track_reset() ((void) 0) +#define aclcheck_track_record(c, o, m) ((void) 0) +#define aclcheck_track_was_checked(c, o) (false) + +#endif /* USE_ASSERT_CHECKING */ + +#endif /* ACLCHECK_TRACK_H */ diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 9f1dd55213d..0a8a2772b23 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -20,6 +20,7 @@ AbsoluteTime AccessMethodInfo AccessPriv Acl +AclCheckEntry AclItem AclMaskHow AclMode -- 2.34.1 --zB/Wek73NRZcta1g-- ^ permalink raw reply [nested|flat] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 44+ 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] 44+ messages in thread
end of thread, other threads:[~2026-07-15 08:37 UTC | newest] Thread overview: 44+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2026-04-27 14:23 [PATCH v20 3/3] Add Assert guard to detect permission check before lock regressions Bertrand Drouvot <[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]> 2026-06-16 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]> 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