agora inbox for pgsql-hackers@postgresql.orghelp / color / mirror / Atom feed
[PATCH v47 4/9] repack code cleanups 326+ messages / 2 participants [nested] [flat]
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v47 4/9] repack code cleanups @ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 326+ messages in thread From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw) --- src/backend/commands/cluster.c | 163 +++++++++++---------------------- 1 file changed, 51 insertions(+), 112 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fd0bfacaae6..c0220cb3380 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; - MemoryContext apply_cxt; bool have_old_tuple = false; - - /* - * Use a separate memory context for the tuples and any memory needed to - * process them. - * - * XXX would this be better with GenerationContextCreate? - */ - apply_cxt = AllocSetContextCreate(TopTransactionContext, - "REPACK - apply", - ALLOCSET_DEFAULT_SIZES); + MemoryContext oldcxt; spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + while (true) { size_t nread; @@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - MemoryContextReset(apply_cxt); + ResetPerTupleExprContext(chgcxt->cc_estate); } /* Cleanup. */ ExecDropSingleTupleTableSlot(spilled_tuple); ExecDropSingleTupleTableSlot(ondisk_tuple); ExecDropSingleTupleTableSlot(old_update_tuple); - MemoryContextDelete(apply_cxt); + + MemoryContextSwitchTo(oldcxt); } /* @@ -2588,27 +2581,17 @@ static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, ChangeContext *chgcxt) { - List *recheck; - /* Put the tuple in the table, but make sure it won't be decoded */ table_tuple_insert(rel, slot, GetCurrentCommandId(true), HEAP_INSERT_NO_LOGICAL, NULL); - /* - * Update indexes with this new tuple. Because we're merely replaying an - * action that already happened, we have no use for the recheck list of - * indexes returned, so just free it. XXX or maybe just leave it? - */ - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - 0, - slot, - NIL, NULL); - list_free(recheck); - + /* Update indexes with this new tuple. */ + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + 0, + slot, + NIL, NULL); pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1); - - ResetPerTupleExprContext(chgcxt->cc_estate); } /* @@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, TM_FailureData tmfd; TU_UpdateIndexes update_indexes; TM_Result res; - List *recheck; /* - * Carry out the update, avoiding logical decoding info. + * Carry out the update, skipping logical decoding for it. */ res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple, GetCurrentCommandId(true), @@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - recheck = ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, - flags, - spilled_tuple, - NIL, NULL); - list_free(recheck); - ResetPerTupleExprContext(chgcxt->cc_estate); + ExecInsertIndexTuples(chgcxt->cc_rri, + chgcxt->cc_estate, + flags, + spilled_tuple, + NIL, NULL); } pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1); @@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot) TM_FailureData tmfd; /* - * Delete tuple from the new heap. - * - * Do it like in simple_heap_delete(), except for 'wal_logical' (and - * except for 'wait'). + * Delete tuple from the new heap, skipping logical decoding for it. */ res = table_tuple_delete(rel, &(slot->tts_tid), GetCurrentCommandId(true), @@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, char relpersistence; bool is_system_catalog; Oid ident_idx_new; - XLogRecPtr wal_insert_ptr, - end_of_wal; - char dummy_rec_data = '\0'; - Relation *ind_refs, - *ind_refs_p; - int nind; + XLogRecPtr end_of_wal; + List *indexrels; ChangeContext chgcxt; /* Like in cluster_rel(). */ @@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, */ ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old); - /* Find "identity index" on the new relation. */ + /* + * The identity index in the new relation appears in the same relative + * position as the corresponding index in the old relation. Find it. + */ ident_idx_new = InvalidOid; - forboth(lc, ind_oids_old, lc2, ind_oids_new) + foreach_oid(ind_old, ind_oids_old) { - Oid ind_old = lfirst_oid(lc); - Oid ind_new = lfirst_oid(lc2); - if (identIdx == ind_old) { - ident_idx_new = ind_new; + ident_idx_new = list_nth_oid(ind_oids_new, + foreach_current_index(ind_old)); break; } } - - /* Should not happen, given our lock on the old relation. */ if (!OidIsValid(ident_idx_new)) - ereport(ERROR, - errmsg("identity index missing on the new relation")); + elog(ERROR, "could not find index matching \"%s\" at the new relation", + get_rel_name(identIdx)); /* Gather information to apply concurrent changes. */ initialize_change_context(&chgcxt, NewHeap, ident_idx_new); @@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * incomplete page; see GetInsertRecPtr), to minimize the amount of data * we need to flush while holding exclusive lock on the source table. */ - wal_insert_ptr = GetInsertRecPtr(); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, /* * Lock all indexes now, not only the clustering one: all indexes need to * have their files swapped. While doing that, store their relation - * references in an array, to handle predicate locks below. + * references in a zero-terminated array, to handle predicate locks below. */ - ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old)); - nind = 0; + indexrels = NIL; foreach_oid(ind_oid, ind_oids_old) { Relation index; @@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, index = index_open(ind_oid, AccessExclusiveLock); /* - * TODO 1) Do we need to check if ALTER INDEX was executed since the - * new index was created in build_new_indexes()? 2) Specifically for - * the clustering index, should check_index_is_clusterable() be called - * here? (Not sure about the latter: ShareUpdateExclusiveLock on the - * table probably blocks all commands that affect the result of - * check_index_is_clusterable().) + * Some things about the index may have changed before we locked the + * index, such as ALTER INDEX RENAME. We don't need to do anything + * here to absorb those changes in the new index. */ - *ind_refs_p = index; - ind_refs_p++; - nind++; + indexrels = lappend(indexrels, index); } /* @@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * Tuples and pages of the old heap will be gone, but the heap will stay. */ TransferPredicateLocksToHeapRelation(OldHeap); - /* The same for indexes. */ - for (int i = 0; i < nind; i++) + foreach_ptr(RelationData, index, indexrels) { - Relation index = ind_refs[i]; - TransferPredicateLocksToHeapRelation(index); - - /* - * References to indexes on the old relation are not needed anymore, - * however locks stay till the end of the transaction. - */ index_close(index, NoLock); } - pfree(ind_refs); + list_free(indexrels); /* - * Flush anything we see in WAL, to make sure that all changes committed - * while we were waiting for the exclusive lock are available for - * decoding. This should not be necessary if all backends had - * synchronous_commit set, but we can't rely on this setting. - * - * Unfortunately, GetInsertRecPtr() may lag behind the actual insert - * position, and GetLastImportantRecPtr() points at the start of the last - * record rather than at the end. Thus the simplest way to determine the - * insert position is to insert a dummy record and use its LSN. - * - * XXX Consider using GetLastImportantRecPtr() and adding the size of the - * last record (plus the total size of all the page headers the record - * spans)? + * Flush WAL again, to make sure that all changes committed while we were + * waiting for the exclusive lock are available for decoding. */ - XLogBeginInsert(); - XLogRegisterData(&dummy_rec_data, 1); - wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP); - XLogFlush(wal_insert_ptr); + XLogFlush(GetXLogInsertRecPtr()); end_of_wal = GetFlushRecPtr(NULL); /* @@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, { Oid ind_old = lfirst_oid(lc); Oid ind_new = lfirst_oid(lc2); - Oid mapped_tables[4]; - - /* Zero out possible results from swapped_relation_files */ - memset(mapped_tables, 0, sizeof(mapped_tables)); + Oid mapped_tables[4] = {0}; swap_relation_files(ind_old, ind_new, (old_table_oid == RelationRelationId), @@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, mapped_tables); #ifdef USE_ASSERT_CHECKING - /* * Concurrent processing is not supported for system relations, so * there should be no mapped tables. */ for (int i = 0; i < 4; i++) - Assert(mapped_tables[i] == 0); + Assert(!OidIsValid(mapped_tables[i])); #endif } @@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_REBUILD_INDEX); - foreach_oid(ind_oid, OldIndexes) + foreach_oid(oldindex, OldIndexes) { - Oid ind_oid_new; + Oid newindex; char *newName; Relation ind; - ind = index_open(ind_oid, ShareUpdateExclusiveLock); + ind = index_open(oldindex, ShareUpdateExclusiveLock); - newName = ChooseRelationName(get_rel_name(ind_oid), + newName = ChooseRelationName(get_rel_name(oldindex), NULL, "repacknew", get_rel_namespace(ind->rd_index->indrelid), false); - ind_oid_new = index_create_copy(NewHeap, false, ind_oid, - ind->rd_rel->reltablespace, newName); - result = lappend_oid(result, ind_oid_new); + newindex = index_create_copy(NewHeap, false, oldindex, + ind->rd_rel->reltablespace, newName); + result = lappend_oid(result, newindex); index_close(ind, NoLock); } -- 2.47.3 --2fxmamo6mu2qbxgv Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
* [PATCH v54 4/5] Error out any process that would block at REPACK @ 2026-04-01 15:35 Antonin Houska <ah@cybertec.at> 0 siblings, 0 replies; 326+ messages in thread From: Antonin Houska @ 2026-04-01 15:35 UTC (permalink / raw) Any process waiting on REPACK to release its lock would actually cause it to deadlock when it tries to upgrade its lock to AEL, losing all work done to that point. We avoid this by teaching the deadlock detector to raise an error when this condition is detected. --- src/backend/commands/repack.c | 47 ++++++++--- src/backend/storage/lmgr/deadlock.c | 15 ++++ src/include/storage/proc.h | 6 +- src/test/modules/injection_points/Makefile | 1 + .../expected/repack_deadlock.out | 63 ++++++++++++++ src/test/modules/injection_points/meson.build | 1 + .../specs/repack_deadlock.spec | 83 +++++++++++++++++++ 7 files changed, 201 insertions(+), 15 deletions(-) create mode 100644 src/test/modules/injection_points/expected/repack_deadlock.out create mode 100644 src/test/modules/injection_points/specs/repack_deadlock.spec diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index b0898ce52d9..d1be6c60e88 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -292,6 +292,18 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) * to understand and we don't lose any functionality. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); + + /* + * Also set the PROC_IN_CONCURRENT_REPACK flag. This makes the + * deadlock checker cause anyone that would conflict with us to error + * out. It's important to set this flag ahead of actually locking the + * relation; it won't of course affect anyone until we do have a lock + * that others can conflict with. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); } /* @@ -494,11 +506,8 @@ RepackLockLevel(bool concurrent) * If indexOid is InvalidOid, the table will be rewritten in physical order * instead of index order. * - * Note that, in the concurrent case, the function releases the lock at some - * point, in order to get AccessExclusiveLock for the final steps (i.e. to - * swap the relation files). To make things simpler, the caller should expect - * OldHeap to be closed on return, regardless CLUOPT_CONCURRENT. (The - * AccessExclusiveLock is kept till the end of the transaction.) + * On return, OldHeap is closed but locked with AccessExclusiveLock - the lock + * will be released at end of the transaction. * * 'cmd' indicates which command is being executed, to be used for error * messages. @@ -1004,10 +1013,8 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * Note that the worker has to wait for all transactions with XID * already assigned to finish. If some of those transactions is * waiting for a lock conflicting with ShareUpdateExclusiveLock on our - * table (e.g. it runs CREATE INDEX), we can end up in a deadlock. - * Not sure this risk is worth unlocking/locking the table (and its - * clustering index) and checking again if it's still eligible for - * REPACK CONCURRENTLY. + * table (e.g. it runs CREATE INDEX), it should encounter ERROR in the + * deadlock checking code. */ start_repack_decoding_worker(tableOid); @@ -3096,7 +3103,19 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, LockRelationOid(OldHeap->rd_rel->reltoastrelid, AccessExclusiveLock); /* - * Tuples and pages of the old heap will be gone, but the heap will stay. + * Now that we have all access-exclusive locks on all relations, we no + * longer want other processes to error out when trying to acquire a + * conflicting lock. Therefore, unset our flag. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags &= ~PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + + /* + * Tuples and pages of the old heap will be gone, but the heap itself will + * stay. In order for predicate locks to continue to work, convert them + * to relation-level locks. We do this both for table and indexes. */ TransferPredicateLocksToHeapRelation(OldHeap); foreach_ptr(RelationData, index, indexrels) @@ -3370,9 +3389,11 @@ start_repack_decoding_worker(Oid relid) /* * The decoding setup must be done before the caller can have XID assigned - * for any reason, otherwise the worker might end up in a deadlock, - * waiting for the caller's transaction to end. Therefore wait here until - * the worker indicates that it has the logical decoding initialized. + * for any reason, otherwise the worker might end up waiting for the + * caller's transaction to end. (Deadlock detector does not consider this + * a conflict because the worker is in the same locking group as the + * backend that launched it.) Therefore wait here until the worker + * indicates that it has the logical decoding initialized. */ ConditionVariablePrepareToSleep(&shared->cv); for (;;) diff --git a/src/backend/storage/lmgr/deadlock.c b/src/backend/storage/lmgr/deadlock.c index b8962d875b6..c20ac682b0d 100644 --- a/src/backend/storage/lmgr/deadlock.c +++ b/src/backend/storage/lmgr/deadlock.c @@ -620,6 +620,21 @@ FindLockCycleRecurseMember(PGPROC *checkProc, proc->statusFlags & PROC_IS_AUTOVACUUM) blocking_autovacuum_proc = proc; + /* + * Similarly, if we note that we're blocked by some + * process running REPACK (CONCURRENTLY), just fail. That + * process is going to upgrade its lock at some point, and + * it would be inappropriate for any other process to + * cause that to fail. + */ + if (checkProc == MyProc && + proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + ereport(ERROR, + errcode(ERRCODE_OBJECT_IN_USE), + errmsg("could not wait for concurrent REPACK"), + errdetail("Process %d waits for REPACK running on process %d", + MyProc->pid, proc->pid)); + /* We're done looking at this proclock */ break; } diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 22822fc68d7..a43cfe53558 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -70,10 +70,12 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_CONCURRENT_REPACK 0x40 /* REPACK (CONCURRENTLY) */ -/* flags reset at EOXact */ +/* flags reset at EOXact. A bit of a misnomer ... */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | \ + PROC_IN_CONCURRENT_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/test/modules/injection_points/Makefile b/src/test/modules/injection_points/Makefile index 2cd7d87c533..f7663859fe2 100644 --- a/src/test/modules/injection_points/Makefile +++ b/src/test/modules/injection_points/Makefile @@ -15,6 +15,7 @@ REGRESS_OPTS = --dlpath=$(top_builddir)/src/test/regress ISOLATION = basic \ inplace \ repack \ + repack_deadlock \ repack_toast \ syscache-update-pruned \ heap_lock_update diff --git a/src/test/modules/injection_points/expected/repack_deadlock.out b/src/test/modules/injection_points/expected/repack_deadlock.out new file mode 100644 index 00000000000..a86e4767536 --- /dev/null +++ b/src/test/modules/injection_points/expected/repack_deadlock.out @@ -0,0 +1,63 @@ +Parsed test spec with 2 sessions + +starting permutation: wait_before_lock add_column wakeup_before_lock check1 +injection_points_attach +----------------------- + +(1 row) + +step wait_before_lock: + REPACK (CONCURRENTLY) repack_deadlock USING INDEX repack_deadlock_pkey; + <waiting ...> +step add_column: + alter table repack_deadlock add column noise text; + <waiting ...> +step add_column: <... completed> +ERROR: could not wait for concurrent REPACK +step wakeup_before_lock: + SELECT injection_points_wakeup('repack-concurrently-before-lock'); + +injection_points_wakeup +----------------------- + +(1 row) + +step wait_before_lock: <... completed> +step check1: + INSERT INTO relfilenodes(node) + SELECT relfilenode FROM pg_class WHERE relname='repack_deadlock'; + + SELECT count(DISTINCT node) FROM relfilenodes; + + SELECT i, j FROM repack_deadlock ORDER BY i, j; + + INSERT INTO data_s1(i, j) + SELECT i, j FROM repack_deadlock; + + SELECT count(*) + FROM data_s1 d1 FULL JOIN data_s2 d2 USING (i, j) + WHERE d1.i ISNULL OR d2.i ISNULL; + +count +----- + 1 +(1 row) + +i|j +-+- +1|1 +2|2 +3|3 +4|4 +(4 rows) + +count +----- + 4 +(1 row) + +injection_points_detach +----------------------- + +(1 row) + diff --git a/src/test/modules/injection_points/meson.build b/src/test/modules/injection_points/meson.build index a414abb924b..1cd88d6db65 100644 --- a/src/test/modules/injection_points/meson.build +++ b/src/test/modules/injection_points/meson.build @@ -46,6 +46,7 @@ tests += { 'basic', 'inplace', 'repack', + 'repack_deadlock', 'repack_toast', 'syscache-update-pruned', 'heap_lock_update', diff --git a/src/test/modules/injection_points/specs/repack_deadlock.spec b/src/test/modules/injection_points/specs/repack_deadlock.spec new file mode 100644 index 00000000000..9d23a6588c2 --- /dev/null +++ b/src/test/modules/injection_points/specs/repack_deadlock.spec @@ -0,0 +1,83 @@ +# Test REPACK with a concurrent transaction that would cause a deadlock +setup +{ + CREATE EXTENSION injection_points; + + CREATE TABLE repack_deadlock(i int PRIMARY KEY, j int); + INSERT INTO repack_deadlock(i, j) VALUES (1, 1), (2, 2), (3, 3), (4, 4); + + CREATE TABLE relfilenodes(node oid); + + CREATE TABLE data_s1(i int, j int); + CREATE TABLE data_s2(i int, j int); +} + +teardown +{ + DROP TABLE repack_deadlock; + DROP EXTENSION injection_points; + + DROP TABLE relfilenodes; + DROP TABLE data_s1; + DROP TABLE data_s2; +} + +session s1 +setup +{ + SELECT injection_points_set_local(); + SELECT injection_points_attach('repack-concurrently-before-lock', 'wait'); +} +# Perform the initial load and wait for s2 to do some data changes. +step wait_before_lock +{ + REPACK (CONCURRENTLY) repack_deadlock USING INDEX repack_deadlock_pkey; +} +# Check the table from the perspective of s1. +# +# Besides the contents, we also check that relfilenode has changed. + +# Have each session write the contents into a table and use FULL JOIN to check +# if the outputs are identical. +step check1 +{ + INSERT INTO relfilenodes(node) + SELECT relfilenode FROM pg_class WHERE relname='repack_deadlock'; + + SELECT count(DISTINCT node) FROM relfilenodes; + + SELECT i, j FROM repack_deadlock ORDER BY i, j; + + INSERT INTO data_s1(i, j) + SELECT i, j FROM repack_deadlock; + + SELECT count(*) + FROM data_s1 d1 FULL JOIN data_s2 d2 USING (i, j) + WHERE d1.i ISNULL OR d2.i ISNULL; +} +teardown +{ + SELECT injection_points_detach('repack-concurrently-before-lock'); +} + +session s2 +# Change the existing data. UPDATE changes both key and non-key columns. Also +# update one row twice to test whether tuple version generated by this session +# can be found. +step add_column +{ + alter table repack_deadlock add column noise text; +} + +step wakeup_before_lock +{ + SELECT injection_points_wakeup('repack-concurrently-before-lock'); +} + +# Test if data changes introduced while one session is performing REPACK +# CONCURRENTLY find their way into the table. +permutation + wait_before_lock + add_column + wakeup_before_lock + check1 -- 2.47.3 --cdhh4t7ukb6tnjoq Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v54-0005-Reserve-replication-slots-specifically-for-REPAC.patch" ^ permalink raw reply [nested|flat] 326+ messages in thread
end of thread, other threads:[~2026-04-01 15:35 UTC | newest] Thread overview: 326+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-03-31 14:48 [PATCH v47 4/9] repack code cleanups Álvaro Herrera <alvherre@kurilemu.de> 2026-04-01 15:35 [PATCH v54 4/5] Error out any process that would block at REPACK Antonin Houska <ah@cybertec.at>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox